Digital Library[ Search Result ]
A Perimeter-Based IoU Loss for Efficient Bounding Box Regression in Object Detection
http://doi.org/10.5626/JOK.2021.48.8.913
In object detection, neural networks are generally trained by minimizing two types of losses simultaneously, namely classification loss and regression loss for bounding boxes. However, the regression loss often fails to achieve its ultimate goal, that is, it often obtains a predicted bounding box that maximally intersects with its target box. This is due to the fact that the regression loss is not highly correlated with the IoU, which actually measures how much the bounding box and its target box overlap with each other. Although several penalty terms have been invented and added to the IoU loss in order to address the problem of regression losses, they still show some inefficiency particularly when penalty terms become zero by enclosing another box or overlapping with the center point before the bounding box and its target box are perfectly the same. In this paper, we propose a perimeter based IoU (PIoU) loss exploiting the perimeter differences of the minimum bounding rectangle of both a predicted box and its target box from those of two boxes themselves. In our experiments using the state-of-the-art object detection models (e.g., YOLO v3, SSD, and FCOS), we show that our PIoU loss consistently achieves better accuracy than all the other existing IoU losses.
A Malicious Traffic Detection Method Using X-means Clustering
Myoungji Han, Jihyuk Lim, Junyong Choi, Hyunjoon Kim, Jungjoo Seo, Cheol Yu, Sung-Ryul Kim, Kunsoo Park
Malicious traffic, such as DDoS attack and botnet communications, refers to traffic that is generated for the purpose of disturbing internet networks or harming certain networks, servers, or hosts. As malicious traffic has been constantly evolving in terms of both quality and quantity, there have been many researches fighting against it. In this paper, we propose an effective malicious traffic detection method that exploits the X-means clustering algorithm. We also suggest how to analyze statistical characteristics of malicious traffic and to define metrics that are used when clustering. Finally, we verify effectiveness of our method by experiments with two released traffic data.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr